Disclosure of Invention
Aiming at the problems, the invention provides an intelligent monitoring system of a numerical control machine tool based on the Internet of things.
The purpose of the invention is realized by adopting the following technical scheme:
the system comprises a plurality of sensors arranged on the numerical control machine, a data collection subsystem used for collecting state information data of the numerical control machine through the sensors, a data processing subsystem used for preprocessing the state information data collected by the data collection subsystem, an Internet of things server used for storing the preprocessed state information data and a user terminal used for displaying the state information data; the data collection subsystem is respectively connected with the sensor and the data processing subsystem, and the data processing subsystem and the user terminal are respectively connected with the Internet of things server; the data processing subsystem comprises a data anomaly detection module and a data fusion processing module, the data anomaly detection module is used for carrying out anomaly detection on the state information data and repairing the detected abnormal data, and the data fusion processing module is used for carrying out fusion processing on the state information data.
Preferably, the data collection subsystem comprises a signal adapter for converting sensor signals into corresponding status information data, the signal adapter being connected to the sensor.
Further, the data collection subsystem further comprises a controller for controlling the acquisition frequency, the controller being connected to the sensor.
The user terminal comprises any one or more of an LED display screen, an LCD display screen, a smart phone, a notebook computer and a desktop computer.
The sensor comprises any one or more of a temperature sensor, a vibration sensor, a liquid level sensor, a displacement sensor, a current sensor and a Hall sensor.
The invention has the beneficial effects that: the invention can facilitate the different user terminals to check the state information data in time, so that the user can know the state information of the numerical control machine tool in time, thereby carrying out proper selection or processing according to the state information of the numerical control machine tool, improving the utilization rate of the numerical control machine tool, meeting the requirement of people on knowing the state information of the numerical control machine tool in real time, and early warning the numerical control machine tool which is likely to have faults in advance, so that the working personnel or maintenance personnel can carry out corresponding processing conveniently, and the loss caused by the machine tool faults is reduced.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1, an embodiment of the present invention provides an intelligent monitoring system for a numerically-controlled machine tool based on the internet of things, which includes a plurality of sensors 1 disposed on the numerically-controlled machine tool, a data collection subsystem 2 for collecting status information data of the numerically-controlled machine tool through the sensors, a data processing subsystem 3 for preprocessing the status information data collected by the data collection subsystem 2, an internet of things server 4 for storing the preprocessed status information data, and a user terminal 5 for displaying the status information data; the data collection subsystem 2 is respectively connected with the sensor 1 and the data processing subsystem 3, and the data processing subsystem 3 and the user terminal 5 are respectively connected with the internet of things server 4.
In one embodiment, the data collection subsystem 2 includes a signal adapter for converting the signals of the sensors 1 into corresponding status information data, the signal adapter being connected to the sensors 1.
Further, the data collection subsystem 2 further comprises a controller for controlling the acquisition frequency, the controller being connected to the sensor.
The user terminal 5 comprises any one or more of an LED display screen, an LCD display screen, a smart phone, a notebook computer and a desktop computer.
The sensor 1 comprises any one or more of a temperature sensor, a vibration sensor, a liquid level sensor, a displacement sensor, a current sensor and a Hall sensor.
The numerical control machine monitoring system designed by the embodiment of the invention can facilitate different user terminals 5 to check the state information data in time, so that a user can know the state information of the numerical control machine in time, and therefore, proper selection or processing can be carried out according to the state information of the numerical control machine, the utilization rate of the numerical control machine is improved, the requirement of people on knowing the state information of the numerical control machine in real time is met, the numerical control machine with possible faults can be pre-warned in advance, so that the corresponding processing can be conveniently carried out by working personnel or maintenance personnel, and the loss caused by the machine faults is reduced.
In one implementation, as shown in fig. 2, the data processing subsystem 3 includes a data anomaly detection module 10 and a data fusion processing module 20, the data anomaly detection module 10 is configured to perform anomaly detection on the state information data and repair the detected anomalous data, and the data fusion processing module 20 is configured to perform fusion processing on the state information data.
In one embodiment, when the sensors 1 are deployed, a monitoring area for monitoring the numerical control machine tool is partitioned, different types of sensors 1 are deployed in each partition, the number of the same type of sensors 1 deployed in different partitions is the same, and data sampling time intervals of the sensors 1 are set to be consistent.
The deployment mode of the sensor 1 of the above embodiment can facilitate subsequent data processing.
In one embodiment, the data anomaly detection module 10 performs anomaly detection on the state information data, specifically including:
(1) setting the width N of the data analysis time window, scanning the status information data sent by the data transceiver module 10 in real time by using the data analysis time window, and scanning a status information data yiIf the normal range exceeds the preset normal range, performing (2); otherwise, judging the state information data to be normal;
(2) calculating the number of scan status informationAccording to yiThe mean, standard deviation and median of the state information data within the time window of data analysis;
(3) if the status information data yiIf the following condition is satisfied, the state information data y is determinediIs normal; otherwise, judging the state information data yiFor anomalous data:
in the formula (I), the compound is shown in the specification,
for scanning the status information data y
iU is the scan state information data y
iThe standard deviation of the state information data within the time window is analyzed.
The abnormal condition of the state information data is two kinds, namely, the abnormal condition is caused by the influence of factors such as the fault of the sensor 1, the fault of the data acquisition terminal, the bad environment and the like, and the abnormal condition is caused by the problem of the working parameters of the numerical control machine. During monitoring, abnormal data acquired due to the fact that working parameters of the numerical control machine tool are in a problem are usually important data and need to be reserved for further data analysis, and abnormal data caused by hardware faults and the like are not real data and need to be repaired.
In view of the above situation, the present embodiment innovatively provides a mechanism for detecting abnormal data, which detects status information data in a window scanning manner, and can more quickly complete the abnormal identification of status information data compared with a manner of detecting status information data one by one, because only the status information data exceeding a preset normal range is detected abnormally; by analyzing the relationship between the state information data beyond the preset normal range and the state information data in the data analysis time window, the actual reason why the state information data exceeds the preset normal range can be judged, and whether the state information data is real data or not is determined.
In an embodiment, the data anomaly detection module 10 repairs the detected anomalous data, specifically including: if the status information data y is judgediReplacing the abnormal data with a repair value for the abnormal data, and marking;
wherein, the calculation formula of the set restoration value is as follows:
wherein y' represents the repair value, max is the maximum value of the state information data in the current data analysis time window, min is the minimum value of the state information data in the current data analysis time window, ymedThe median value of the state information data within the time window is analyzed for the current data.
When the data anomaly detection module 10 repairs the detected anomalous data, the repair value of the replaced anomalous data is obtained according to the set calculation formula of the repair value, wherein the calculation formula calculates the repair value of the replaced anomalous data by combining the mean value and the median value of the state information data in the data analysis time window.
In an embodiment, the data fusion processing module 20 performs fusion processing on the state information data, specifically: the sensors 1 belonging to the same type and the same partition are regarded as the same fusion component unit, and the state information data belonging to the same fusion component unit is subjected to fusion processing in units of time periods.
The fusion processing is performed on the state information data belonging to the same fusion component unit by taking a time period as a unit, and the fusion processing specifically comprises the following steps:
(1) taking the state information data belonging to the same fusion composition unit as basic data participating in fusion, calculating the average value of the basic data of each time period corresponding to each sensor 1, and calculating the quantity of the marked state information data in each time period corresponding to each sensor 1;
(2) extracting the average value of the basic data of each sensor 1 in the same time period as the data to be fused to form a data sequence to be fused
k is the number of the extracted average values of the basic data, and the noise variance of the sensor 1 corresponding to each data to be fused is obtained;
(3) calculating the reliability of the sensor 1 corresponding to each data to be fused:
in the formula, E
iIndicating the sensor 1, E corresponding to the ith data to be fused
lRepresents the sensor 1 corresponding to the ith data to be fused,
indicating the sensor 1E
iThe degree of reliability of the optical waveguide is high,
is a sensor 1E
iThe variance of the noise of (a) is,
is a sensor 1E
lThe noise variance of (2);
in order to ensure that the sensor 1E is in the time period corresponding to the ith data to be fused
iThe number of marked state information data in the collected state information data;
in order to ensure that the sensor 1E is in the time period corresponding to the ith data to be fused
iThe number of marked state information data in the collected state information data;
(4) the data sequence to be fused is treated according to the following formula
Carrying out fusion treatment:
in the formula, y represents the fusion result.
In the embodiment, the characteristics of multi-source state information data are considered, and a data fusion processing mechanism is innovatively provided, which considers the problem of time-space matching of data and performs fusion processing on state information data belonging to the same fusion component unit by taking a time period as a unit, so that fusion data of the same region in the same period can be obtained. In this embodiment, when fusion processing is performed on data to be fused, the problem of reliability of the sensor 1 to which the data to be fused belongs is considered, the reliability of the sensor 1 is used as the weight of the data to be fused, and a fusion value is calculated based on a weighted average method, so that the calculated fusion value can be closer to the actual situation, and the data accuracy is higher.
In this embodiment, a calculation formula of the reliability of the sensor 1 is designed based on two aspects of the number of times that the sensor 1 acquires abnormal data and the noise variance, and the performance of the sensor 1 in the aspect of data acquisition precision can be objectively measured, so that a good foundation is laid for accurately calculating a fusion value, and the precision of the intelligent monitoring system of the numerically-controlled machine tool based on the internet of things in the aspects of data acquisition and data processing is further improved.
From the above description of embodiments, it is clear for a person skilled in the art that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For a hardware implementation, the modules may be implemented in one or more of the following units: an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to perform the functions described herein, or a combination thereof. For a software implementation, some or all of the procedures of an embodiment may be performed by a computer program instructing associated hardware. In practice, the program may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. Computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.